Predictive Likelihood Ratios for Language Model Watermark Detection

• URL: http://arxiv.org/abs/2609.15657v1
• Date: Mon, 14 Sep 2026 14:39:29 GMT
• Title: Predictive Likelihood Ratios for Language Model Watermark Detection
• Abstract summary: Keyed watermark detection tests dependence between observed tokens and pseudorandom variables reconstructed from a secret key.<n>We construct predictive likelihood ratios that average over uncertain probability deficits and residual-tail distributions.
• Score: 3.8200540264474907
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Keyed watermark detection tests dependence between observed tokens and pseudorandom variables reconstructed from a secret key. Building on the pivotal framework of Li et al. (2025), we construct predictive likelihood ratios that average over uncertain probability deficits and residual-tail distributions. The aim is robust detection power across alternative specifications without requiring a single signal-strength tuning. A mixture prior combines tail shape and effective width; hierarchical extensions allow within-document variation in deficit or width. The test maximizes prior-averaged power at a fixed size, but is not generally uniformly most powerful or minimax. Under the exact conditional pivot null, normalized predictive alternatives selected before each observation yield a Bayes factor that is also a test martingale: Type I error control is unaffected by alternative misspecification and remains valid under optional stopping. This guarantee does not cover violations of the conditional null, and the interpolated implementation has no certified anytime guarantee. Gumbel marginal likelihoods are evaluated by fixed quadrature. Across the evaluated tail-shape and tail-width alternatives and three horizons, the union-tail mixture has maximum observed Type II error regret .0080, compared with .0962 for the equal-tail mixture, relative to the best tested rule. On temperature-matched outputs from two open models, it improves AUC over the equal-tail baseline in all eight non-saturated model-temperature cells, although the leading reference score generally has higher AUC. Supplementary experiments show retained power under independent null-like replacement and smaller changes from hierarchical dependence modeling. The evidence supports robustness across the evaluated alternatives, not uniform power guarantees or resistance to arbitrary text edits.

Related papers

• EDGE: a closed-form directed test for the calibration of probabilistic binary classifiers [0.0]
  We propose EDGE, a calibration test for the canonical probabilistic classifier, logistic regression.<n> EDGE reads the same binned predicted-observed table a reliability diagram plots, and projects its standardized bin residuals onto a small pre-specified basis of smooth calibration-distortion.<n>Across link and feature misspecification the pre-specified default led or tied every rival binned test on the fitted index in 19 of 22 detectable scenarios, and stayed computable where the refit-based Stukel score test separates in 20% to 28% of samples.
  arXiv  Detail & Related papers  (2026-08-20T19:06:05Z)
• Denoised Conformal Alignment for Reliable Selection of Conditional Average Treatment Effect Predictions [10.945117945979566]
  We study reliable selection for black-box CATE predictors.<n>We construct doubly robust proxy errors from pseudo-outcomes.<n>We propose Denoised Conformal Alignment.
  arXiv  Detail & Related papers  (2026-07-03T10:00:28Z)
• A prior-free blind detection of information leakage from model predictions [0.0]
  We give a decision-theoretic framework in which leakage diagnostics are functionals of the predicted-risk/outcome law.<n>A recalibrated leak matching an honest model's calibration and discrimination is indistinguishable from honest performance by emphany function of the predictions.<n>A near-deterministic subgroup produces a sustained unit-purity head that no legitimate predictor of a non-deterministic outcome can manufacture.
  arXiv  Detail & Related papers  (2026-06-09T05:13:03Z)
• Testing the Test: Score-Direction Instability in Class-Split Anomaly Detection [56.362776482614976]
  Within-dataset class-split evaluation is widely used as a proxy for fully unconditional out-of-distribution anomaly detection.<n>We show that this protocol can become ill-posed when the held-out anomaly class overlaps the normal mixture in representation space.<n>We introduce a simple training-free diagnostic, neighborhood class leakage, and show that it predicts score-direction instability across Fashion-MNIST, CIFAR-10, and Imagenette.
  arXiv  Detail & Related papers  (2026-05-23T06:27:42Z)
• Towards Anytime-Valid Statistical Watermarking [63.02116925616554]
  We develop the first e-value-based watermarking framework, Anchored E-Watermarking, that unifies optimal sampling with anytime-valid inference.<n>Our framework can significantly enhance sample efficiency, reducing the average token budget required for detection by 13-15% relative to state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-02-19T18:32:26Z)
• LEC: Linear Expectation Constraints for False-Discovery Control in Selective Prediction and Routing Systems [95.35293543918762]
  Large language models (LLMs) often generate unreliable answers, while uncertainty methods fail to fully distinguish correct from incorrect predictions.<n>We address this issue through the lens of false discovery rate (FDR) control, ensuring that among all accepted predictions, the proportion of errors does not exceed a target risk level.<n>We propose LEC, which reinterprets selective prediction as a constrained decision problem by enforcing a Linear Expectation Constraint.
  arXiv  Detail & Related papers  (2025-12-01T11:27:09Z)
• Calibrated Decomposition of Aleatoric and Epistemic Uncertainty in Deep Features for Inference-Time Adaptation [3.018583625592182]
  Most estimators collapse all uncertainty modes into a single confidence score, preventing reliable reasoning about when to allocate more compute or adjust inference.<n>We introduce Uncertainty-Guided Inference-Time Selection, a lightweight inference time framework that disentangles aleatoric (data-driven) and model-driven uncertainty directly in deep feature space.
  arXiv  Detail & Related papers  (2025-11-15T23:47:30Z)
• Unsupervised Conformal Inference: Bootstrapping and Alignment to Control LLM Uncertainty [49.19257648205146]
  We propose an unsupervised conformal inference framework for generation.<n>Our gates achieve close-to-nominal coverage and provide tighter, more stable thresholds than split UCP.<n>The result is a label-free, API-compatible gate for test-time filtering.
  arXiv  Detail & Related papers  (2025-09-26T23:40:47Z)
• Multidimensional Uncertainty Quantification via Optimal Transport [87.97146725546502]
  We take a multidimensional view on uncertainty quantification (UQ) by stacking complementary UQ measures into a vector.<n>VecUQ-OT shows high efficiency even when individual measures fail.
  arXiv  Detail & Related papers  (2025-09-26T14:09:03Z)
• COIN: Uncertainty-Guarding Selective Question Answering for Foundation Models with Provable Risk Guarantees [51.5976496056012]
  COIN is an uncertainty-guarding selection framework that calibrates statistically valid thresholds to filter a single generated answer per question.<n>COIN estimates the empirical error rate on a calibration set and applies confidence interval methods to establish a high-probability upper bound on the true error rate.<n>We demonstrate COIN's robustness in risk control, strong test-time power in retaining admissible answers, and predictive efficiency under limited calibration data.
  arXiv  Detail & Related papers  (2025-06-25T07:04:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.